A soil layer tunneling cutter damage state detection method

Abstract

This invention relates to the field of image processing technology, specifically to a method for detecting the damage status of tunnel boring machine (TBM) cutterhead and face regions in several monitoring frames. The method includes: acquiring point cloud data of the cutterhead region and face region of a TBM in several monitoring frames; constructing a sequence of changes in the TBM monitoring position based on the displacement changes of corresponding data points in the same TBM monitoring region between adjacent monitoring frames; obtaining the monitoring change correlation degree for each TBM monitoring position change degree based on the correlation between these sequences; obtaining the structural confidence score of each TBM image point in each monitoring frame based on the differences between different TBM monitoring position changes in the cutterhead region; and performing data cleaning on the TBM based on the structural confidence score of each image point. This invention cleans up data points in the point cloud data that are significantly affected by interference, improving the accuracy of the detection results.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and more specifically to a method for detecting the damage status of tunneling tools in soil layers. Background Technology

[0002] As one of the most important tools in tunnel excavation projects, tunnel boring machine (TBM) cutters are mainly used to excavate underground tunnels. It is necessary to promptly detect the damage status of the cutter surface to ensure the production quality of the TBM cutters. Current technologies typically utilize point cloud data to collect and characterize cutter information on the TBM cutter surface, thereby enabling damage detection through point cloud data technology.

[0003] Existing technologies typically utilize the PL-ICP algorithm to identify and control the operating status of tunnel boring machines (TBMs) by processing point cloud data. However, this process is affected by environmental factors such as vibration and the soil structure at the tunnel face in different working segments. As a result, different data points in the point cloud data of different parts of the TBM cutter contain varying degrees of interference information, making it difficult to determine the damage status of the TBM cutter and reducing the accuracy of the detection results. Summary of the Invention

[0004] This invention provides a method for detecting the damage status of tunnel boring machine (TBM) cutters in soil layers, in order to solve the existing problem: In the process of identifying and controlling the operating status of the TBM by processing point cloud data, the PL-ICP algorithm is affected by environmental factors such as vibration and the soil structure of the tunnel face in different working segments. This results in different data points in the point cloud data of different parts of the TBM cutter having different degrees of interference information, making it difficult to determine the damage status of the TBM cutter.

[0005] The present invention provides a method for detecting the damage status of tunneling tools in soil layers, which adopts the following technical solution:

[0006] Includes the following steps:

[0007] Point cloud data of the cutterhead area and the working face area of ​​the tunnel boring machine are collected in several monitoring frames. The point cloud data contains multiple shield image points with three-dimensional spatial location information. Each shield image point corresponds to a data point in each monitoring frame.

[0008] The cutterhead area and the tunnel face area of ​​the tunnel boring machine (TBM) are both categorized as a single TBM monitoring area. Based on the displacement changes of corresponding data points in the point cloud data of the same TBM monitoring area between adjacent monitoring frames, a sequence of TBM monitoring position changes for each TBM monitoring area is constructed. The correlation between the TBM monitoring position changes in different TBM monitoring areas is used to obtain the monitoring change correlation degree of each TBM monitoring position change in the cutterhead area's sequence. Finally, the structural confidence of each TBM image point in each monitoring frame is obtained based on the differences between different TBM monitoring position changes in the cutterhead area.

[0009] Data cleaning for the tunnel boring machine is performed based on the structural confidence level of each tunnel boring machine image point.

[0010] Preferably, the specific method for constructing a shield monitoring position change sequence for each shield monitoring area based on the displacement changes of corresponding data points in the point cloud data of the same shield monitoring area between adjacent monitoring frames includes:

[0011] Preset a window with a preset side length For any shield tunneling monitoring area, any shield image point within the monitoring area is recorded as the target shield image point; for any monitoring frame within the monitoring area, the data point corresponding to the target shield image point in the monitoring frame is recorded as the target shield monitoring data point of the target shield image point; with the target shield monitoring data point as the center, the window size is... The window area is denoted as the neighborhood data point area of ​​the target shield tunnel monitoring data point; obtain the neighborhood data point areas of all target shield tunnel monitoring data points of the target shield tunnel image point;

[0012] For any two adjacent target shield monitoring data points of a target shield image point, the first target shield monitoring data point is designated as the reference shield monitoring data point, and the second target shield monitoring data point is designated as the marked shield monitoring data point. The degree of neighborhood variation of the marked shield monitoring data point is obtained based on the distance of the variation difference between the data points in the corresponding neighborhood data point area between the reference shield monitoring data point and the marked shield monitoring data point.

[0013] Based on the degree of change in the neighborhood, the change in the shield monitoring position of the shield monitoring area in each monitoring frame is obtained;

[0014] The sequence of all shield monitoring position changes in the shield monitoring area is denoted as the shield monitoring position change sequence of the shield monitoring area.

[0015] Preferably, the method for obtaining the degree of neighborhood variation of the marked shield tunneling monitoring data point based on the distance of the variation difference between data points in the corresponding neighborhood data point area between the reference shield tunneling monitoring data point and the marked shield tunneling monitoring data point includes:

[0016]

[0017] In the formula, This indicates the degree of neighborhood variation of the marked shield tunneling monitoring data points; This indicates the number of all data points in the neighborhood data point region of the reference shield tunneling monitoring data point; This indicates the number of all data points in the neighborhood data point region that marks the shield tunneling monitoring data point; This indicates the first neighboring data point in the region of the reference shield tunneling monitoring data point. The data point, and the neighboring data point region of the marked shield tunnel monitoring data point. Euclidean distance between data points.

[0018] Preferably, the specific method for obtaining the degree of change of the shield monitoring position in each monitoring frame based on the degree of change in the neighborhood monitoring area includes:

[0019] The sum of the neighborhood variation of all target shield image points and marked shield monitoring data points is recorded as the sum of neighborhood variation of the shield monitoring area in the monitoring frame. The sum of neighborhood variation of the shield monitoring area in all monitoring frames is linearly normalized, and the sum of neighborhood variation of each normalized monitoring frame is recorded as the shield monitoring position change degree.

[0020] Preferably, the method for obtaining the correlation degree of monitoring change of each shield monitoring position in the shield monitoring position change sequence of the shield machine cutterhead area based on the correlation of shield monitoring position change sequences between different shield monitoring areas includes:

[0021] Preset a reference number for the degree of change in the shield tunneling monitoring position. ; Record any one of the shield monitoring position changes in the shield machine cutterhead area as the target shield monitoring position change, and denote the left side of the target shield monitoring position change as the target shield monitoring position change. The change in the monitoring position of the individual shield tunneling machine and the change in the monitoring position of the target shield tunneling machine are shown on the right. The data segment consisting of the changes in the monitored positions of each shield tunnel is denoted as the neighborhood reference data segment of the changes in the monitored positions of the target shield tunnel.

[0022] Obtain the shield region association value for each shield monitoring position change in the neighborhood reference data segment of the target shield monitoring position change;

[0023] Any one of the shield monitoring position changes in the shield monitoring position change sequence in the cutterhead area of ​​the tunnel boring machine is denoted as the first target shield monitoring position change. The monitoring change correlation factor of the first target shield monitoring position change is obtained based on the shield area correlation value of the overall shield monitoring position change within the neighborhood reference data segment of the first target shield monitoring position change.

[0024] In the sequence of shield monitoring position changes in the cutterhead area of ​​the tunnel boring machine (TBM), the product of the monitoring change correlation factor of the first shield monitoring position change and the monitoring change correlation factor of the second shield monitoring position change is recorded as the monitoring change correlation degree of the second shield monitoring position change; the product of the monitoring change correlation degree of the second shield monitoring position change and the monitoring change correlation factor of the third shield monitoring position change is recorded as the monitoring change correlation degree of the third shield monitoring position change; the product of the monitoring change correlation degree of the third shield monitoring position change and the monitoring change correlation factor of the fourth shield monitoring position change is recorded as the monitoring change correlation degree of the fourth shield monitoring position change; and so on, to obtain the monitoring change correlation degree of each shield monitoring position change.

[0025] Preferably, the specific method for obtaining the shield region association value of each shield monitoring position change in the neighborhood reference data segment of the target shield monitoring position change is as follows:

[0026] Any shield monitoring position change in the neighborhood reference data segment of the target shield monitoring position change is recorded as the reference shield monitoring position change; the index of the reference shield monitoring position change in the shield monitoring position change sequence in the shield machine cutterhead area is recorded as the target index; the shield monitoring position change in the shield face area with the same index as the target index is recorded as the reference shield monitoring position change; the shield monitoring position change sequence in the shield machine cutterhead area and the shield monitoring position change sequence in the tunnel face area are input into the DTW dynamic time warping algorithm to obtain the DTW distance between the reference and reference shield monitoring position change, and this distance is recorded as the shield area association value of the reference shield monitoring position change.

[0027] Preferably, the specific method for obtaining the monitoring change correlation factor of the first target shield tunnel monitoring position change based on the shield area correlation value of the overall shield tunnel monitoring position change within the neighborhood reference data segment of the first target shield tunnel monitoring position change degree includes:

[0028]

[0029] In the formula, The monitoring change correlation factor represents the degree of change in the monitoring position of the first target shield. The neighborhood reference data segment representing the degree of change in the monitoring position of the first target shield tunneling machine; The neighborhood reference data segment representing the degree of change in the monitoring position of the first target shield tunneling machine. The degree of change in the location of each shield tunneling machine is correlated with the shield tunneling area value. This represents an exponential function with the natural constant as its base.

[0030] Preferably, the method for obtaining the structural confidence level of each shield image point in each monitoring frame based on the differences in the degree of change of different shield monitoring positions in the shield machine cutterhead area includes:

[0031] In the sequence of shield monitoring position changes in the cutterhead area of ​​the tunnel boring machine, the absolute value of the difference between any two different shield monitoring position changes is used as the distance metric. Hierarchical clustering is performed on all shield monitoring position changes to obtain several clusters.

[0032] According to the cutterhead area of ​​the tunnel boring machine, in the... The differences between different shield monitoring position changes within the cluster to which the shield monitoring position change belongs, and the differences between the shield machine cutterhead area and the shield machine monitoring position change. The shield tunneling image point at the first The degree of neighborhood change in the frame is monitored to obtain the first [frame name] of the shield machine cutterhead region. The shield tunneling image point at the first Frame monitoring: structural confidence factor within frames;

[0033] Obtain all shield image points in the cutterhead area of ​​the tunnel boring machine at the first... The structural confidence factor in the frame is monitored, and all structural confidence factors are linearly normalized. Each normalized structural confidence factor is recorded as a structural confidence level.

[0034] Preferably, the step of determining the cutterhead region of the tunnel boring machine in the first... The differences between different shield monitoring position changes within the cluster to which the shield monitoring position change belongs, and the differences between the shield machine cutterhead area and the shield machine monitoring position change. The shield tunneling image point at the first The degree of neighborhood change in the frame is monitored to obtain the first [frame name] of the shield machine cutterhead region. The shield tunneling image point at the first The specific methods for monitoring the structural confidence factor in frames are as follows:

[0035]

[0036] In the formula, The first area representing the cutterhead region of the tunnel boring machine The shield tunneling image point at the first Frame monitoring: structural confidence factor within frames; This indicates the total number of monitoring frames in the cutterhead area of ​​the tunnel boring machine; Indicates the first The data point at the th th Frame monitoring detects the degree of neighborhood changes within a frame; The first area representing the cutterhead region of the tunnel boring machine The number of all shield tunnel monitoring position changes in the cluster to which a shield tunnel monitoring position change belongs; Indicates the first The cluster to which the shield tunneling monitoring location change belongs is the [number]th [item]. The degree of change in the location of each tunnel boring machine; Indicates the first The mean of all shield tunneling monitoring position changes in the cluster to which the shield tunneling monitoring position change belongs; This represents the preset hyperparameters.

[0037] Preferably, the specific method for cleaning the tunnel boring machine data based on the structural confidence level of each tunnel boring machine image point includes:

[0038] Preset a structural confidence threshold If the shield machine cutterhead area is the first The shield tunneling image point at the first The confidence level of the structure in the frame monitoring frame is less than The first section of the tunnel boring machine cutterhead area The shield tunneling image point at the first The data points in the frame monitoring frame are replaced with the data points in the shield machine cutterhead area. The shield tunneling image point at the first Frame monitoring of data points within a frame.

[0039] The beneficial effects of the technical solution of this invention are as follows: Based on the displacement changes of corresponding data points in the point cloud data of the same shield tunneling monitoring area between adjacent monitoring frames, a sequence of shield tunneling monitoring position change degrees is constructed for each shield tunneling monitoring area; based on the correlation between shield tunneling monitoring position change degrees in the sequence, the monitoring change correlation degree of each shield tunneling monitoring position change degree is obtained; based on the differences between different shield tunneling monitoring position change degrees in the shield machine cutterhead area, the structural confidence degree of each shield image point in each monitoring frame is obtained; data cleaning of the shield machine is performed based on the structural confidence degree of each shield image point; wherein the monitoring change correlation degree is used to describe the degree to which the point cloud data of the shield machine changes slowly with geological changes during actual operation, making the point cloud data better represent the relationship affected by geological changes; the structural confidence degree is used to describe the degree of drastic changes in the corresponding image structure in the monitoring frame, making the change relationship of the corresponding three-dimensional position information in the point cloud data clearer; this invention cleans up data points in the point cloud data that are subject to significant interference, improving the accuracy of the detection results. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a flowchart illustrating the steps of a method for detecting the damage status of tunneling tools in soil layers according to the present invention. Detailed Implementation

[0042] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a method for detecting the damage state of tunneling tools in soil layers according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0044] The following describes in detail, with reference to the accompanying drawings, a specific scheme for a method for detecting the damage status of tunneling tools in soil layers provided by the present invention.

[0045] Please see Figure 1The diagram illustrates a flowchart of a method for detecting the damage state of tunneling tools in soil layers, according to an embodiment of the present invention. The method includes the following steps:

[0046] Step S001: Collect point cloud data of the cutterhead area and the tunnel face area of ​​the tunnel boring machine in several monitoring frames.

[0047] It should be noted that existing technologies typically use the PL-ICP algorithm to identify and control the operating status of tunnel boring machines by processing point cloud data. However, this process is affected by environmental factors such as vibration and the soil structure at the tunnel face in different working segments. As a result, the point cloud data of different parts of the tunnel boring machine cutter are interfered with to varying degrees, making it difficult to determine the damage to the cutter and reducing the accuracy of the detection results.

[0048] Specifically, the first step is to collect point cloud data and several monitoring frames for each shield tunneling monitoring area. The process is as follows: The shield machine's cutterhead area and face area are both designated as the shield machine monitoring area; point cloud data for each monitoring area is acquired using 3D laser scanning, and each data point in the point cloud data is recorded as a shield image point; taking any given shield machine monitoring area as an example, several monitoring frames for that area over the past day are obtained from the shield machine's historical monitoring frame database, with each frame taken every 5 seconds; several monitoring frames for each shield machine monitoring area are then acquired. The time interval and total duration of recording monitoring frames can be determined based on the specific implementation requirements.

[0049] It should be noted that the cutterhead area of ​​the tunnel boring machine mainly consists of the main beam, auxiliary beam, roller cutter, scraper, side scraper, and over-excavation cutter; the face area mainly consists of the working face area during the tunnel boring machine's advancement process; the point cloud data of each tunnel boring machine monitoring area contains multiple data points, and each data point corresponds to a data point with three-dimensional spatial location information in each monitoring frame, and the three-dimensional spatial location corresponding to each data point is not always the same in different monitoring frames.

[0050] Thus, point cloud data of the tunnel boring machine cutterhead area and the tunnel face area in several monitoring frames were obtained using the above method.

[0051] Step S002: Based on the displacement changes of corresponding data points in the point cloud data of the same shield monitoring area between adjacent monitoring frames, construct a sequence of shield monitoring position changes for each shield monitoring area; based on the correlation between the shield monitoring position changes in the sequence of shield monitoring position changes in different shield monitoring areas, obtain the monitoring change correlation degree of each shield monitoring position change in the shield monitoring position change sequence of the shield machine cutterhead area; based on the differences between different shield monitoring position changes in the shield machine cutterhead area, obtain the structural confidence degree of each shield image point in each monitoring frame.

[0052] It should be noted that the image data related to the tunnel boring machine's operating environment mainly includes point cloud data of the cutterhead assembly structure in the cutterhead area and point cloud data of the corresponding soil structure in the tunnel face area. The positions of different data points in the point cloud data are affected by environmental factors such as vibration and the soil structure of the tunnel face in different operating segments, making it difficult to determine the degree of wear on different data points in each shield monitoring area. When the positions of corresponding data points change within multiple monitoring frames, the positions of the data points caused by wear will slowly change over time. Therefore, by combining the change characteristics of structural points in the shield monitoring area, the structural confidence of each data point can be obtained, so as to achieve accurate cleaning of data points and complete the accurate visualization processing of the tunnel boring machine cutter and operating environment.

[0053] Preferably, in one embodiment of the present invention, a sequence of shield monitoring position changes for each shield monitoring area is obtained based on the displacement changes of corresponding data points in the point cloud data of the same shield monitoring area between adjacent monitoring frames. The specific method includes:

[0054] Preset a window with a preset side length In this embodiment, This example is used for illustration; no specific limitations are set in this embodiment. This can be determined based on the specific implementation situation; taking any shield tunneling monitoring area as an example, any shield tunneling image point in that monitoring area is recorded as the target shield tunneling image point; taking any monitoring frame in that monitoring area as an example, the data point corresponding to the target shield tunneling image point in that monitoring frame is recorded as the target shield tunneling monitoring data point of the target shield tunneling image point; with the target shield tunneling monitoring data point as the center, the window size is... The window area is denoted as the neighborhood data point area of ​​the target shield tunnel monitoring data point; the neighborhood data point areas of all target shield tunnel monitoring data points of the target shield tunnel image point are obtained. Each target shield tunnel monitoring data point corresponds to one monitoring frame.

[0055] Furthermore, taking any two adjacent target shield tunneling machine monitoring data points as an example, the first target shield tunneling machine monitoring data point is designated as the reference monitoring data point, and the second target shield tunneling machine monitoring data point is designated as the marked monitoring data point. The degree of neighborhood variation of the marked monitoring data point is obtained based on the distance of the variation difference between the data points in the corresponding neighborhood data point regions between the reference monitoring data point and the marked monitoring data point. As an example, the degree of neighborhood variation of the marked monitoring data point can be calculated using the following formula:

[0056]

[0057] In the formula, This indicates the degree of neighborhood variation of the marked shield tunneling monitoring data points; This indicates the number of all data points in the neighborhood data point region of the reference shield tunneling monitoring data point; This indicates the number of all data points in the neighborhood data point region that marks the shield tunneling monitoring data point; This indicates the first neighboring data point in the region of the reference shield tunneling monitoring data point. The data point, and the neighboring data point region of the marked shield tunnel monitoring data point. The Euclidean distance between the data points. The method for obtaining the Euclidean distance is a well-known technique and will not be described further in this embodiment.

[0058] It should be noted that, This indicates the degree of change in the overall data points within the corresponding neighborhood data point area between the marked shield tunneling monitoring data point and the reference shield tunneling monitoring data point. The greater the degree of change in the neighborhood of the marked shield tunneling monitoring data point, the greater the change in the point cloud data of the shield tunneling monitoring area within the monitoring frame to which the marked shield tunneling monitoring data point belongs, reflecting a more obvious change in the appearance of the monitored object in the monitoring frame to which the marked shield tunneling monitoring data point belongs.

[0059] Furthermore, the degree of neighborhood variation of the marked shield monitoring data points for all target shield image points is obtained; the sum of the degree of neighborhood variation of the marked shield monitoring data points for all target shield image points is recorded as the sum of the neighborhood variation of the shield monitoring area in the monitoring frame; the sum of the neighborhood variation of the shield monitoring area in all monitoring frames is linearly normalized, and the normalized sum of the neighborhood variation of each monitoring frame is recorded as the shield monitoring position change degree; the sequence of all shield monitoring position change degrees in the shield monitoring area is recorded as the shield monitoring position change degree sequence of the shield monitoring area; the shield monitoring position change degree sequence of each shield monitoring area is obtained. Each monitoring frame corresponds to one sum of neighborhood variation of the shield monitoring area.

[0060] It should be further noted that, for the tunnel face area, the sequence of changes in the monitored shield location will show a phased trend with the regional changes in the geological structure; while for the cutterhead area, when wear occurs in the cutterhead area, it will show a consistent change in direction at multiple stages, with the regional location change continuously increasing. However, it will be affected by changes in the tunnel face area and environmental factors such as mud accumulation, leading to misjudgments of the wear location in the cutterhead area. Therefore, the correlation between the location changes of the two monitored shield areas can be used to further analyze the reliability of the location changes in the cutterhead area.

[0061] Preferably, in one embodiment of the present invention, the monitoring change correlation degree of each shield monitoring position change degree in the shield monitoring position change degree sequence in the shield machine cutterhead area is obtained based on the correlation between the shield monitoring position change degree sequences in different shield monitoring areas. The specific method includes:

[0062] Preset a reference number for the degree of change in the shield tunneling monitoring position. In this embodiment, This example is used for illustration; no specific limitations are set in this embodiment. It can be determined according to the specific implementation situation; taking any one of the shield monitoring position change sequences in the shield machine cutterhead area as an example, the left side of the shield monitoring position change... The degree of change of the shield tunneling monitoring position and the right side of the degree of change of the shield tunneling monitoring position. The data segment consisting of the changes in the shield tunneling machine's monitored position is denoted as the neighborhood reference data segment for that change in the shield tunneling machine's monitored position. It should be noted that if the number of changes in the shield tunneling machine's monitored position on either side does not meet the preset threshold... Then, based on the actual number of shield monitoring position changes on the left and right sides of the shield monitoring position change, the neighborhood reference data segment of the shield monitoring position change is obtained.

[0063] Furthermore, any shield monitoring position change in the neighborhood reference data segment of the shield monitoring position change is recorded as the reference shield monitoring position change; the index of the reference shield monitoring position change in the shield monitoring position change sequence is recorded as the target index; the shield monitoring position change in the tunnel face region with the same index as the target index is recorded as the reference shield monitoring position change; the shield monitoring position change sequence of the cutterhead region and the shield monitoring position change sequence of the tunnel face region are input into the DTW dynamic time warping algorithm to obtain the DTW distance between the reference and reference shield monitoring position change, and this distance is recorded as the shield region association value of the reference shield monitoring position change; the shield region association values ​​of all shield monitoring position changes in the neighborhood reference data segment of the shield monitoring position change are obtained. The process of obtaining the DTW distance between two data sequences is a well-known part of the DTW (Dynamic Time Warping) algorithm, and will not be described in detail in this embodiment.

[0064] Furthermore, taking any one of the shield monitoring position changes in the shield monitoring position change sequence in the cutterhead area of ​​the tunnel boring machine (TBM) as an example, the monitoring change correlation factor of this shield monitoring position change is obtained based on the shield region correlation value of the overall shield monitoring position change within the neighborhood reference data segment of this shield monitoring position change. As an example, the monitoring change correlation factor of this shield monitoring position change can be calculated using the following formula:

[0065]

[0066] In the formula, The monitoring change correlation factor represents the degree of change in the monitored location of the tunnel boring machine; The neighboring reference data segment represents the degree of change in the monitored location of the tunnel boring machine; The neighborhood reference data segment representing the degree of change in the monitored position of the tunnel boring machine (TBM) The degree of change in the location of each shield tunneling machine is correlated with the shield tunneling area value. This represents an exponential function with the natural constant as its base. The example uses... The model is used to represent the inverse proportional relationship and for normalization processing. As input to the model, implementers can choose between an inverse proportional function and a normalization function based on actual conditions. The model obtains the monitoring change correlation factors for all shield monitoring position changes in the shield monitoring position change sequence within the shield machine cutterhead area.

[0067] It should be noted that the larger the correlation factor of the monitoring change of the shield tunneling location, the more slowly the point cloud data of the shield tunneling machine changes with geological changes during actual operation.

[0068] Furthermore, in the sequence of shield monitoring position changes in the cutterhead area of ​​the tunnel boring machine (TBM), the product of the monitoring change correlation factor of the first shield monitoring position change and the monitoring change correlation factor of the second shield monitoring position change is recorded as the monitoring change correlation degree of the second shield monitoring position change; the product of the monitoring change correlation degree of the second shield monitoring position change and the monitoring change correlation factor of the third shield monitoring position change is recorded as the monitoring change correlation degree of the third shield monitoring position change; the product of the monitoring change correlation degree of the third shield monitoring position change and the monitoring change correlation factor of the fourth shield monitoring position change is recorded as the monitoring change correlation degree of the fourth shield monitoring position change; the product of the monitoring change correlation degree of the fourth shield monitoring position change and the monitoring change correlation factor of the fifth shield monitoring position change is recorded as the monitoring change correlation degree of the fifth shield monitoring position change; and so on, to obtain the monitoring change correlation degree of all shield monitoring position changes. It should be noted that after calculating the correlation degree of the monitoring change of all shield tunneling monitoring position changes, this embodiment defaults to the monitoring change correlation factor of the first shield tunneling monitoring position change as the monitoring change correlation degree of the first shield tunneling monitoring position change.

[0069] Preferably, in one embodiment of the present invention, the structural confidence level of each shield image point in each monitoring frame is obtained based on the differences in the degree of change between different shield monitoring positions in the shield machine cutterhead area. The specific method includes:

[0070] In the sequence of shield monitoring position changes in the cutterhead area of ​​the tunnel boring machine (TBM), the absolute value of the difference between any two different shield monitoring position changes is used as a distance metric. Hierarchical clustering is then performed on all shield monitoring position changes to obtain several clusters. Each cluster contains multiple shield monitoring position changes. Furthermore, the process of clustering based on the distance metric is a well-known aspect of hierarchical clustering algorithms and will not be elaborated upon in this embodiment.

[0071] Furthermore, based on the cutterhead area of ​​the tunnel boring machine in the first... The differences between different shield monitoring position changes within the cluster to which the shield monitoring position change belongs, and the differences between the shield machine cutterhead area and the shield machine monitoring position change. The shield tunneling image point at the first The degree of neighborhood change in the frame is monitored to obtain the first [frame name] of the shield machine cutterhead region. The shield tunneling image point at the first The structural confidence factor in the frame is monitored. As an example, the first structural confidence factor in the cutterhead region of the tunnel boring machine can be calculated using the following formula. The shield tunneling image point at the first Frame monitoring: structural confidence factor in frames:

[0072]

[0073] In the formula, The first area representing the cutterhead region of the tunnel boring machine The shield tunneling image point at the first Frame monitoring: structural confidence factor within frames; This indicates the total number of monitoring frames in the cutterhead area of ​​the tunnel boring machine; Indicates the first The data point at the th th Frame monitoring detects the degree of neighborhood changes within a frame; The first area representing the cutterhead region of the tunnel boring machine The number of all shield tunnel monitoring position changes in the cluster to which a shield tunnel monitoring position change belongs; Indicates the first The cluster to which the shield tunneling monitoring location change belongs is the [number]th [item]. The degree of change in the location of each tunnel boring machine; Indicates the first The mean of all shield tunneling monitoring position changes in the cluster to which the shield tunneling monitoring position change belongs; This represents the preset hyperparameters; in this embodiment, the preset hyperparameters are... This is used to prevent the denominator from being 0; This indicates taking the absolute value.

[0074] It should be noted that if the first [section / area] of the tunnel boring machine cutterhead area... The shield tunneling image point at the first The smaller the structure confidence factor in the frame monitoring frame, the better the structure confidence factor. The data point at the th th The more drastic the changes in the corresponding image structure within a frame, the more it reflects the... The data point at the th th The more data information is in a frame, the more it needs to be cleaned.

[0075] Furthermore, all shield image points in the cutterhead area of ​​the tunnel boring machine are acquired in the [missing information - likely a specific location or process]. The structural confidence factor in the frame is monitored, and all structural confidence factors are linearly normalized. Each normalized structural confidence factor is recorded as a structural confidence level.

[0076] Thus, the structural confidence level of each shield tunneling image point in each monitoring frame is obtained using the above method.

[0077] Step S003: Perform data cleaning on the tunnel boring machine based on the structural confidence of each tunnel boring machine image point.

[0078] Preferably, in another embodiment of the present invention, data cleaning of the tunnel boring machine is performed based on the structural confidence level of each shield image point, including the following specific methods:

[0079] Preset a structural confidence threshold In this embodiment, This example is used for illustration; no specific limitations are set in this embodiment. It depends on the specific implementation situation; if the shield machine cutterhead area is the first The shield tunneling image point at the first The confidence level of the structure in the frame monitoring frame is less than The first section of the tunnel boring machine cutterhead area The shield tunneling image point at the first The data points in the frame monitoring frame are replaced with the data points in the shield machine cutterhead area. The shield tunneling image point at the first Frame monitoring of data points within the frame. Based on the data points in the shield machine cutterhead area. A BIM model is constructed from the data points of each shield tunneling image point in all monitoring frames. Visual inspection is then performed based on the BIM model to obtain the visual inspection results. Constructing the BIM model is a well-known technique, and the process of obtaining the visual inspection results from the BIM model is based on the well-known PL-ICP (Point-to-line Iterative ClosestPoint) algorithm, which will not be elaborated upon in this embodiment.

[0080] It should be noted that if the first [section / area] of the tunnel boring machine cutterhead area... The structural confidence of each shield tunneling image point in the last monitoring frame is less than [a certain value]. The first section of the shield machine cutterhead area The location information of each shield tunneling image point in the last monitoring frame is removed.

[0081] This concludes the embodiment.

[0082] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for detecting the damage state of tunneling tools in soil layers, characterized in that, The method includes the following steps: Point cloud data of the cutterhead area and the working face area of ​​the tunnel boring machine are collected in several monitoring frames. The point cloud data contains multiple shield image points with three-dimensional spatial location information. Each shield image point corresponds to a data point in each monitoring frame. The cutterhead area and the tunnel face area of ​​the tunnel boring machine (TBM) are both categorized as a single TBM monitoring area. Based on the displacement changes of corresponding data points in the point cloud data of the same TBM monitoring area between adjacent monitoring frames, a sequence of TBM monitoring position changes for each TBM monitoring area is constructed. The correlation between the TBM monitoring position changes in different TBM monitoring areas is used to obtain the monitoring change correlation degree of each TBM monitoring position change in the cutterhead area's sequence. Finally, the structural confidence of each TBM image point in each monitoring frame is obtained based on the differences between different TBM monitoring position changes in the cutterhead area. Data cleaning of the tunnel boring machine is performed based on the structural confidence level of each tunnel boring machine image point; The specific method for constructing a shield monitoring position change sequence for each shield monitoring area based on the displacement changes of corresponding data points in the point cloud data of the same shield monitoring area between adjacent monitoring frames includes: Preset a window with a preset side length For any shield tunneling monitoring area, any shield image point within the monitoring area is recorded as the target shield image point; for any monitoring frame within the monitoring area, the data point corresponding to the target shield image point in the monitoring frame is recorded as the target shield monitoring data point of the target shield image point; with the target shield monitoring data point as the center, the window size is... The window area is denoted as the neighborhood data point area of ​​the target shield tunnel monitoring data point; obtain the neighborhood data point areas of all target shield tunnel monitoring data points of the target shield tunnel image point; For any two adjacent target shield monitoring data points of a target shield image point, the first target shield monitoring data point is designated as the reference shield monitoring data point, and the second target shield monitoring data point is designated as the marked shield monitoring data point. The degree of neighborhood variation of the marked shield monitoring data point is obtained based on the distance of the variation difference between the data points in the corresponding neighborhood data point area between the reference shield monitoring data point and the marked shield monitoring data point. Based on the degree of change in the neighborhood, the change in the shield monitoring position of the shield monitoring area in each monitoring frame is obtained; The sequence of all shield monitoring position changes in the shield monitoring area is denoted as the shield monitoring position change sequence of the shield monitoring area. The method for obtaining the correlation degree of monitoring change of each shield monitoring position in the shield monitoring position change sequence in the shield machine cutterhead area based on the correlation between shield monitoring position change sequences in different shield monitoring areas includes the following specific methods: Preset a reference number for the degree of change in the shield tunneling monitoring position. ; Record any one of the shield monitoring position changes in the shield machine cutterhead area as the target shield monitoring position change, and denote the left side of the target shield monitoring position change as the target shield monitoring position change. The change in the monitoring position of the individual shield tunneling machine and the change in the monitoring position of the target shield tunneling machine are shown on the right. The data segment consisting of the changes in the monitored positions of each shield tunnel is denoted as the neighborhood reference data segment of the changes in the monitored positions of the target shield tunnel. Obtain the shield region association value for each shield monitoring position change in the neighborhood reference data segment of the target shield monitoring position change; Any one of the shield monitoring position changes in the shield monitoring position change sequence in the cutterhead area of ​​the tunnel boring machine is denoted as the first target shield monitoring position change. The monitoring change correlation factor of the first target shield monitoring position change is obtained based on the shield area correlation value of the overall shield monitoring position change within the neighborhood reference data segment of the first target shield monitoring position change. In the sequence of shield monitoring position changes in the cutterhead area of ​​the tunnel boring machine (TBM), the product of the monitoring change correlation factor of the first shield monitoring position change and the monitoring change correlation factor of the second shield monitoring position change is recorded as the monitoring change correlation degree of the second shield monitoring position change; the product of the monitoring change correlation degree of the second shield monitoring position change and the monitoring change correlation factor of the third shield monitoring position change is recorded as the monitoring change correlation degree of the third shield monitoring position change; the product of the monitoring change correlation degree of the third shield monitoring position change and the monitoring change correlation factor of the fourth shield monitoring position change is recorded as the monitoring change correlation degree of the fourth shield monitoring position change; and so on, to obtain the monitoring change correlation degree of each shield monitoring position change. The method for obtaining the structural confidence level of each shield image point in each monitoring frame based on the differences in the degree of change of different shield monitoring positions in the shield machine cutterhead area includes the following: In the sequence of shield monitoring position changes in the cutterhead area of ​​the tunnel boring machine, the absolute value of the difference between any two different shield monitoring position changes is used as the distance metric. Hierarchical clustering is performed on all shield monitoring position changes to obtain several clusters. According to the cutterhead area of ​​the tunnel boring machine, in the... The differences between different shield monitoring position changes within the cluster to which the shield monitoring position change belongs, and the differences between the shield machine cutterhead area and the shield machine monitoring position change. The shield tunneling image point at the first The degree of neighborhood change in the frame is monitored to obtain the first [frame name] of the shield machine cutterhead region. The shield tunneling image point at the first Frame monitoring: structural confidence factor within frames; Obtain all shield image points in the cutterhead area of ​​the tunnel boring machine at the first... The structural confidence factor in the frame is monitored, and all structural confidence factors are linearly normalized. Each normalized structural confidence factor is recorded as a structural confidence level.

2. The method for detecting the damage state of tunneling tools in soil layers according to claim 1, characterized in that, The method for determining the degree of neighborhood variation of the marked shield tunneling monitoring data point based on the distance of variation differences between corresponding neighboring data points within the area between the reference shield tunneling monitoring data point and the marked shield tunneling monitoring data point includes the following specific methods: In the formula, This indicates the degree of neighborhood variation of the marked shield tunneling monitoring data points; This indicates the number of all data points in the neighborhood data point region of the reference shield tunneling monitoring data point; This indicates the number of all data points in the neighborhood data point region that marks the shield tunneling monitoring data point; This indicates the first neighboring data point in the region of the reference shield tunneling monitoring data point. The data point, and the neighboring data point region of the marked shield tunnel monitoring data point. Euclidean distance between data points.

3. The method for detecting the damage state of tunneling tools in soil layers according to claim 1, characterized in that, The specific method for obtaining the degree of change in the shield monitoring position of the shield monitoring area in each monitoring frame based on the degree of change in the neighborhood is as follows: The sum of the neighborhood changes of all target shield image points and marked shield monitoring data points is recorded as the sum of the neighborhood changes of the shield monitoring area in the monitoring frame. The sum of neighborhood changes of the shield tunneling monitoring area across all monitoring frames is linearly normalized, and the sum of neighborhood changes of each normalized monitoring frame is recorded as the shield tunneling monitoring position change degree.

4. The method for detecting the damage state of tunneling tools in soil layers according to claim 1, characterized in that, The specific method for obtaining the shield region association value of each shield monitoring position change in the neighborhood reference data segment of the target shield monitoring position change is as follows: The change in the target shield monitoring position is recorded as any shield monitoring position change in the neighborhood reference data segment; the index of the reference shield monitoring position change in the shield monitoring position change sequence in the shield machine cutterhead area is recorded as the target index. The shield monitoring position change degree with the same sequence number as the target sequence in the shield monitoring position change degree sequence of the tunnel face area is recorded as the reference shield monitoring position change degree. The shield monitoring position change degree sequence of the shield machine cutterhead area and the shield monitoring position change degree sequence of the tunnel face area are input into the DTW dynamic time warping algorithm to obtain the DTW distance between the reference shield monitoring position change degree and the reference shield monitoring position change degree, and recorded as the shield area association value of the reference shield monitoring position change degree.

5. The method for detecting the damage state of tunneling tools in soil layers according to claim 1, characterized in that, The method for obtaining the monitoring change correlation factor of the first target shield monitoring position change based on the shield region correlation value of the overall shield monitoring position change within the neighborhood reference data segment of the first target shield monitoring position change degree includes: In the formula, The monitoring change correlation factor represents the degree of change in the monitoring position of the first target shield. The neighborhood reference data segment representing the degree of change in the monitoring position of the first target shield tunneling machine; The neighborhood reference data segment representing the degree of change in the monitoring position of the first target shield tunneling machine. The degree of change in the location of each shield tunneling machine is correlated with the shield tunneling area value. This represents an exponential function with the natural constant as its base.

6. The method for detecting the damage state of tunneling tools in soil layers according to claim 1, characterized in that, The information based on the cutterhead area of ​​the tunnel boring machine in the first The differences between different shield monitoring position changes within the cluster to which the shield monitoring position change belongs, and the differences between the shield machine cutterhead area and the shield machine monitoring position change. The shield tunneling image point at the first The degree of neighborhood change in the frame is monitored to obtain the first [frame name] of the shield machine cutterhead region. The shield tunneling image point at the first The specific methods for monitoring the structural confidence factor in frames are as follows: In the formula, The first area representing the cutterhead region of the tunnel boring machine The shield tunneling image point at the first Frame monitoring: structural confidence factor within frames; This indicates the total number of monitoring frames in the cutterhead area of ​​the tunnel boring machine; Indicates the first The data point at the th th Frame monitoring detects the degree of neighborhood changes within a frame; The first area representing the cutterhead region of the tunnel boring machine The number of all shield tunnel monitoring position changes in the cluster to which a shield tunnel monitoring position change belongs; Indicates the first The cluster to which the shield tunneling monitoring location change belongs is the [number]th [item]. The degree of change in the location of each tunnel boring machine; Indicates the first The mean of all shield tunneling monitoring position changes in the cluster to which the shield tunneling monitoring position change belongs; This represents the preset hyperparameters.

7. The method for detecting the damage state of tunneling tools in soil layers according to claim 1, characterized in that, The specific method for data cleaning of the tunnel boring machine based on the structural confidence of each shield image point includes: Preset a structural confidence threshold If the shield machine cutterhead area is the first The shield tunneling image point at the first The confidence level of the structure in the frame monitoring frame is less than The first section of the tunnel boring machine cutterhead area The shield tunneling image point at the first The data points in the frame monitoring frame are replaced with the data points in the shield machine cutterhead area. The shield tunneling image point at the first Frame monitoring of data points within a frame.

Images